Cargando…

Enchondroma Detection from Hand Radiographs with an Interactive Deep Learning Segmentation Tool—A Feasibility Study

Enchondromas are common benign bone tumors, usually presenting in the hand. They can cause symptoms such as swelling and pain but often go un-noticed. If the tumor expands, it can diminish the bone cortices and predispose the bone to fracture. Diagnosis is based on clinical investigation and radiogr...

Descripción completa

Detalles Bibliográficos
Autores principales: Anttila, Turkka Tapio, Aspinen, Samuli, Pierides, Georgios, Haapamäki, Ville, Laitinen, Minna Katariina, Ryhänen, Jorma
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10672653/
https://www.ncbi.nlm.nih.gov/pubmed/38002741
http://dx.doi.org/10.3390/jcm12227129
_version_ 1785149541272518656
author Anttila, Turkka Tapio
Aspinen, Samuli
Pierides, Georgios
Haapamäki, Ville
Laitinen, Minna Katariina
Ryhänen, Jorma
author_facet Anttila, Turkka Tapio
Aspinen, Samuli
Pierides, Georgios
Haapamäki, Ville
Laitinen, Minna Katariina
Ryhänen, Jorma
author_sort Anttila, Turkka Tapio
collection PubMed
description Enchondromas are common benign bone tumors, usually presenting in the hand. They can cause symptoms such as swelling and pain but often go un-noticed. If the tumor expands, it can diminish the bone cortices and predispose the bone to fracture. Diagnosis is based on clinical investigation and radiographic imaging. Despite their typical appearance on radiographs, they can primarily be misdiagnosed or go totally unrecognized in the acute trauma setting. Earlier applications of deep learning models to image classification and pattern recognition suggest that this technique may also be utilized in detecting enchondroma in hand radiographs. We trained a deep learning model with 414 enchondroma radiographs to detect enchondroma from hand radiographs. A separate test set of 131 radiographs (47% with an enchondroma) was used to assess the performance of the trained deep learning model. Enchondroma annotation by three clinical experts served as our ground truth in assessing the deep learning model’s performance. Our deep learning model detected 56 enchondromas from the 62 enchondroma radiographs. The area under receiver operator curve was 0.95. The F1 score for area statistical overlapping was 69.5%. Our deep learning model may be a useful tool for radiograph screening and raising suspicion of enchondroma.
format Online
Article
Text
id pubmed-10672653
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-106726532023-11-16 Enchondroma Detection from Hand Radiographs with an Interactive Deep Learning Segmentation Tool—A Feasibility Study Anttila, Turkka Tapio Aspinen, Samuli Pierides, Georgios Haapamäki, Ville Laitinen, Minna Katariina Ryhänen, Jorma J Clin Med Article Enchondromas are common benign bone tumors, usually presenting in the hand. They can cause symptoms such as swelling and pain but often go un-noticed. If the tumor expands, it can diminish the bone cortices and predispose the bone to fracture. Diagnosis is based on clinical investigation and radiographic imaging. Despite their typical appearance on radiographs, they can primarily be misdiagnosed or go totally unrecognized in the acute trauma setting. Earlier applications of deep learning models to image classification and pattern recognition suggest that this technique may also be utilized in detecting enchondroma in hand radiographs. We trained a deep learning model with 414 enchondroma radiographs to detect enchondroma from hand radiographs. A separate test set of 131 radiographs (47% with an enchondroma) was used to assess the performance of the trained deep learning model. Enchondroma annotation by three clinical experts served as our ground truth in assessing the deep learning model’s performance. Our deep learning model detected 56 enchondromas from the 62 enchondroma radiographs. The area under receiver operator curve was 0.95. The F1 score for area statistical overlapping was 69.5%. Our deep learning model may be a useful tool for radiograph screening and raising suspicion of enchondroma. MDPI 2023-11-16 /pmc/articles/PMC10672653/ /pubmed/38002741 http://dx.doi.org/10.3390/jcm12227129 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Anttila, Turkka Tapio
Aspinen, Samuli
Pierides, Georgios
Haapamäki, Ville
Laitinen, Minna Katariina
Ryhänen, Jorma
Enchondroma Detection from Hand Radiographs with an Interactive Deep Learning Segmentation Tool—A Feasibility Study
title Enchondroma Detection from Hand Radiographs with an Interactive Deep Learning Segmentation Tool—A Feasibility Study
title_full Enchondroma Detection from Hand Radiographs with an Interactive Deep Learning Segmentation Tool—A Feasibility Study
title_fullStr Enchondroma Detection from Hand Radiographs with an Interactive Deep Learning Segmentation Tool—A Feasibility Study
title_full_unstemmed Enchondroma Detection from Hand Radiographs with an Interactive Deep Learning Segmentation Tool—A Feasibility Study
title_short Enchondroma Detection from Hand Radiographs with an Interactive Deep Learning Segmentation Tool—A Feasibility Study
title_sort enchondroma detection from hand radiographs with an interactive deep learning segmentation tool—a feasibility study
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10672653/
https://www.ncbi.nlm.nih.gov/pubmed/38002741
http://dx.doi.org/10.3390/jcm12227129
work_keys_str_mv AT anttilaturkkatapio enchondromadetectionfromhandradiographswithaninteractivedeeplearningsegmentationtoolafeasibilitystudy
AT aspinensamuli enchondromadetectionfromhandradiographswithaninteractivedeeplearningsegmentationtoolafeasibilitystudy
AT pieridesgeorgios enchondromadetectionfromhandradiographswithaninteractivedeeplearningsegmentationtoolafeasibilitystudy
AT haapamakiville enchondromadetectionfromhandradiographswithaninteractivedeeplearningsegmentationtoolafeasibilitystudy
AT laitinenminnakatariina enchondromadetectionfromhandradiographswithaninteractivedeeplearningsegmentationtoolafeasibilitystudy
AT ryhanenjorma enchondromadetectionfromhandradiographswithaninteractivedeeplearningsegmentationtoolafeasibilitystudy